© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10597
    Prev
    Next
    INDEX
    Explanations

    shell structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Typed
    -0.08
    ết
    -0.08
    rott
    -0.08
    人被
    -0.08
    à¦ĺ
    -0.08
    à§įতà§ģ
    -0.08
    åħ¨ç«Ļ
    -0.08
    .generated
    -0.07
    der
    -0.07
    ÙĪØ«
    -0.07
    POSITIVE LOGITS
    adre
    0.07
     Coch
    0.07
     chứa
    0.06
    à¹Ģà¸Īริà¸į
    0.06
    æĽ´é«ĺçļĦ
    0.06
    缴è¾ĸ
    0.06
    omencl
    0.06
    ear
    0.06
    å±Ĥ级
    0.06
    shell
    0.06
    Activations Density 0.001%

    No Known Activations